k8scat

LLM Wiki

A pattern for building personal knowledge bases using LLMs.

This is an idea file, it is designed to be copy pasted to your own LLM Agent (e.g. OpenAI Codex, Claude Code, OpenCode / Pi, or etc.). Its goal is to communicate the high level idea, but your agent will build out the specifics in collaboration with you.

The core idea

Most people's experience with LLMs and documents looks like RAG: you upload a collection of files, the LLM retrieves relevant chunks at query time, and generates an answer. This works, but the LLM is rediscovering knowledge from scratch on every question. There's no accumulation. Ask a subtle question that requires synthesizing five documents, and the LLM has to find and piece together the relevant fragments every time. Nothing is built up. NotebookLM, ChatGPT file uploads, and most RAG systems work this way.

k8scat

Linux 命令行编辑快捷键

初学者在Linux命令窗口（终端）敲命令时，肯定觉得通过输入一串一串的字符的方式来控制计算是效率很低。 但是Linux命令解释器（Shell）是有很多快捷键的，熟练掌握可以极大的提高操作效率。 下面列出最常用的快捷键，这还不是完全版。

• 命令行快捷键：
  • 常用：
    • Ctrl L ：清屏
• Ctrl M ：等效于回车

k8scat

# Hello, and welcome to makefile basics.
#
# You will learn why `make` is so great, and why, despite its "weird" syntax,
# it is actually a highly expressive, efficient, and powerful way to build
# programs.
#
# Once you're done here, go to
# http://www.gnu.org/software/make/manual/make.html
# to learn SOOOO much more.

k8scat

 # What to do when mysqldump fails
 function report_mysqldump_fail() {
   cat $scratch/${filename}_raw.err >> $log
   mailx -s "mysqldump failed for DB $db_name on $HOSTNAME!!!" emailme@none.com < $log
   exit 2
 }

 # How to report a step along the process
 function status_report() {
   message=$1

k8scat

// ==UserScript==
// @name         Copy Link for GitHub Issues and PRs
// @namespace    http://tampermonkey.net/
// @version      0.2
// @description  Add a "Copy link" button to Github issue and pull requests
// @author       ye11ow, K8sCat <k8scat@gmail.com>
// @match        https://github.com/*
// @include      https://github.com/*/issues/*
// @include      https://github.com/*/pull/*
// @icon         https://www.google.com/s2/favicons?domain=github.com

k8scat

urlencode() {
    # urlencode <string>

    old_lc_collate=$LC_COLLATE
    LC_COLLATE=C

    local length="${#1}"
    for (( i = 0; i < length; i++ )); do
        local c="${1:$i:1}"
        case $c in

k8scat

# Stop dance for OpenResty
# A modification of the Nginx systemd script
# Source: https://www.digitalocean.com/community/tutorials/how-to-use-the-openresty-web-framework-for-nginx-on-ubuntu-16-04
# =======================
#
# ExecStop sends SIGSTOP (graceful stop) to the Nginx process.
# If, after 5s (--retry QUIT/5) OpenResty is still running, systemd takes control
# and sends SIGTERM (fast shutdown) to the main process.
# After another 5s (TimeoutStopSec=5), and if OpenResty is alive, systemd sends
# SIGKILL to all the remaining processes in the process group (KillMode=mixed).

k8scat

#!/usr/bin/env bash
#
# gh-dl-release! It works!
# 
# This script downloads an asset from latest or specific Github release of a
# private repo. Feel free to extract more of the variables into command line
# parameters.
#
# PREREQUISITES
#

k8scat

#!/bin/bash
# bash generate random alphanumeric string
#

# bash generate random 32 character alphanumeric string (upper and lowercase) and 
NEW_UUID=$(cat /dev/urandom | tr -dc 'a-zA-Z0-9' | fold -w 32 | head -n 1)

# bash generate random 32 character alphanumeric string (lowercase only)
cat /dev/urandom | tr -dc 'a-zA-Z0-9' | fold -w 32 | head -n 1

k8scat

package main

import (
    "fmt"
	  "log"
    "net"
    "net/mail"
	  "net/smtp"
    "crypto/tls"
)